Forecasting Analysis of Stock Prices on European Markets Using the ARIMA-GARCH Model

Abstract

The achievement of profits when trading on the stock markets is conditioned by a quality analytical forecast of the development of stock prices in the coming period. This research attempts to compare the results of the ARIMA model and the ARIMA-GARCH model to forecast the development of stock prices on a sample of selected stocks from the Czech, German, Austrian, Polish and British markets. The 4 most liquid titles from each of the above-mentioned markets were selected for the sample of analyzed stocks. Available daily closing stock price data, mostly from the period 2000–2022, were used for the analysis. Research has shown that for most of the analyzed titles, it is more appropriate to use the ARIMA-GARCH model, which better captures variability for this data than just the ARIMA model. The quality of the selected model is evaluated by autocorrelation, heteroskedasticity tests, and Theil´s inequality coefficient.

Keywords

• arima
• garch
• stock price prediction
• time series